© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76743
    Prev
    Next
    INDEX
    Explanations

    names of places in India

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on long, multi-syllabic romanized names and terms (especially South Indian place, temple, and dish names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lucre
    -0.83
     LTC
    -0.82
    ánló
    -0.76
    сени
    -0.75
    Artikel
    -0.75
    Udo
    -0.75
     precau
    -0.73
    Torn
    -0.72
    Tors
    -0.72
     ardour
    -0.71
    POSITIVE LOGITS
    TestSuite
    0.82
    Outros
    0.81
    抓住
    0.80
     puedas
    0.77
    €”
    0.76
     ※
    0.75
    soporte
    0.75
    slideshow
    0.75
    Descriptor
    0.73
    ※
    0.73
    Activations Density 0.008%

    No Known Activations